Kjell Tore Guttormsen 5be9c8e47c feat(ultraplan-local): v1.6.0 — /ultraresearch-local deep research command

Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.

New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.

Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.

Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

2026-04-08 08:58:35 +02:00

3.8 KiB

Raw Blame History

type

created

question

confidence

dimensions

mcp_servers_used

local_agents_used

external_agents_used

ultraresearch-brief

YYYY-MM-DD

{research question}

0.0-1.0

N

list

list

list

{Research Question Title}

Generated by ultraresearch-local v{version} on {YYYY-MM-DD}

Research Question

{The full research question as clarified during interview.}

Executive Summary

{3 sentences maximum. The answer, the confidence level, and the key caveat.}

Dimensions

Each dimension represents one facet of the research question, explored by both local and external agents. Confidence is rated per dimension.

{Dimension Name} -- Confidence: {high | medium | low | contradictory}

Local findings:

{Finding with source citation (file path or agent name)}

External findings:

{Finding with source citation (URL)}

Contradictions:

{If local and external disagree, explain both sides with evidence. Omit this sub-section if no contradictions exist for this dimension.}

Repeat for each dimension.

Local Context

Findings from codebase analysis agents. Omit sub-sections where no relevant findings exist.

Architecture

{Architecture patterns, tech stack, relevant components from architecture-mapper}

Dependencies

{Import chains, data flow, external integrations from dependency-tracer}

Conventions

{Coding patterns, naming, test conventions from convention-scanner}

History

{Recent changes, code ownership, hot files from git-historian}

External Knowledge

Findings from external research agents. Omit sub-sections where no relevant findings exist.

Best Practice

{Official documentation, recommended patterns from docs-researcher}

Alternatives

{Other approaches, competing solutions from community-researcher + contrarian-researcher}

Security

{CVEs, audit history, supply chain risks from security-researcher}

Known Issues

{Common pitfalls, gotchas, real-world problems from community-researcher}

Gemini Second Opinion

Independent research result from Gemini Deep Research. Provides a second perspective for triangulation. Omit this section if gemini-bridge was not used or was unavailable.

{Gemini findings reformatted into key findings, sources cited, and areas of agreement/disagreement with other agents.}

Synthesis

Cross-cutting insights that emerge from combining local and external knowledge. This is NOT a summary of the sections above. It is NEW insight from triangulation -- things that only become visible when local context meets external knowledge.

{Example: "The codebase uses pattern X (local), but best practice has shifted to pattern Y (external). However, our dependency on Z (local) makes a direct migration impractical -- a hybrid approach using Y for new code while maintaining X for existing modules is the pragmatic path."}

Open Questions

Things that remain unresolved after research. Each is a candidate for follow-up research or an assumption to carry forward.

{Question 1 -- why it remains open}
{Question 2 -- why it remains open}

Recommendation

If the research was decision-relevant, provide a concrete recommendation with reasoning. If the research was exploratory (understanding, not deciding), omit this section entirely.

{Recommendation with rationale, citing specific findings from above.}

Sources

#	Source	Type	Quality	Used in
1	{URL or codebase path}	{official / community / codebase / gemini}	{high / medium / low}	{dimension name}

Quality assessment:

high — official documentation, verified codebase analysis, peer-reviewed
medium — reputable community source, well-maintained blog, established project
low — unverified, outdated (>1 year), single-source claim, opinion piece

3.8 KiB Raw Blame History